Select the Quick tab of the Comparing 2 Proportions: Power Calculation Parameters dialog box to access options to enter baseline parameters for power calculations for the Z-test for comparing two proportions.

Fixed Parameters. The entries in the boxes under Fixed Parameters establish the fixed, or baseline, parameters for subsequent power calculations and graphs. Parameters that are not varied explicitly as the independent (X-axis) variables in a graphical analysis will be set equal to these values.

Pi1. In the Pi1 box, enter the population proportion for the population from which group 1 was sampled.

Pi2. In the Pi2 box, enter the mean for the population from which group 2 was sampled.

N1. In the N1 box, enter the sample size for group 1 in the analysis.

N2. In the N2 box, enter the sample size for group 2 in the analysis.

Alpha. In the Alpha box, enter the type I error rate used in determining the critical value for the Z-statistic.

Type of Calculation. Use the options under Type of Calculation to control operation of the dialog box controls for N1 and N2, and to select whether or not the test statistic employs a continuity correction.

Equal N. Select the Equal N check box to limit group 1 and group 2 to the same sample size. If this check box is selected, N1 and N2 are constrained to be equal, only the N1 edit field is enabled, and N2 is varied in synchrony with N1. If the check box is not selected, N1 and N2 can be varied independently.

Continuity Correction. Select the Continuity Correction check box to correct the Z-statistic for continuity.

Type of Hypothesis. Use the option buttons under Type of Hypothesis to determine the type of null hypothesis tested by the Z-statistic.

2-tailed (Pi1 = Pi2). Select the 2-tailed (Pi1 = Pi2) option button to use null and alternative hypotheses of the form

H0:
π1

1-tailed (Pi1 <= Pi2). Select the 1-tailed (Pi1 <= Pi2) option button to use null and alternative hypotheses of the form

H0:
π1 ≤

1-tailed (Pi1 >= Pi2). Select the 1-tailed (Pi1 >= Pi2) option button to use null and alternative hypotheses of the form

H0:
π1